System Specifications
Compute Nodes
| Type | # Nodes | CPU | GPU | RAM | Local Storage | Slingshot Network Cards |
|---|---|---|---|---|---|---|
| CPU | 768 | 2x AMD EPYC™ 9655 96 cores per CPU 192 cores per node |
- | 768 GB DDR5 | - | 1x |
| GPU | 192 | 2x AMD EPYC™ 9655 96 cores per CPU 192 cores per node |
8x NVIDIA H200 141 GB HBM3e per GPU NV18 NVLink between GPUs within a node |
2.25 TB DDR5 | 15.36 TB NVMe | 4x |
| Large Memory | 16 | 2x AMD EPYC™ 9554 64 cores per CPU 128 cores per node |
- | 4 TB DDR5 | 30 TB NVMe | 1x |
Network
- HPE Slingshot 400 interconnect
- Dragonfly Plus topology
- 400 Gbps HPE Cassini network interface cards with HPE Rosetta switches
Storage
Warning
All data on NSCC systems is governed by the Data Management and Retention Policy. Read it carefully to prevent data loss, maintain proper access, and manage your data securely.
| Directory | Filesystem | Capacity | Mount Point | Quota | Use Case |
|---|---|---|---|---|---|
| Home | Lustre | 2.5 PB | /home/users/<org>/<institution>/<username> |
50 GB per user | Long term storage of user data |
| Project | Lustre | 37 PB | /data/projects/<project-id> |
Per project allocation | Long term storage of project data shared among members |
| Scratch | Lustre | 24 PB | /scratch/users/<org>/<institution>/<username> |
100 TB per user | Temporary storage of user data for better I/O performance (subject to purge) |